Advertisement

Ensemble Prostate Tumor Classification in H&E Whole Slide Imaging via Stain Normalization and Cell Density Estimation

  • Michaela Weingant
  • Hayley M. Reynolds
  • Annette Haworth
  • Catherine Mitchell
  • Scott Williams
  • Matthew D. DiFrancoEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9352)

Abstract

Classification of prostate tumor regions in digital histology images requires comparable features across datasets. Here we introduce adaptive cell density estimation and apply H&E stain normalization into a supervised classification framework to improve inter-cohort classifier robustness. The framework uses Random Forest feature selection, class-balanced training example subsampling and support vector machine (SVM) classification to predict the presence of high- and low-grade prostate cancer (HG-PCa and LG-PCa) on image tiles. Using annotated whole-slide prostate digital pathology images to train and test on two separate patient cohorts, classification performance, as measured with area under the ROC curve (AUC), was 0.703 for HG-PCa and 0.705 for LG-PCa. These results improve upon previous work and demonstrate the effectiveness of cell-density and stain normalization on classification of prostate digital slides across cohorts.

Keywords

Machine learning Digital pathology Tumor prediction Prostate Cell counting 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Borren, A., Groenendaal, G., Moman, M.R., Boeken Kruger, A.E., van Diest, P.J., van Vulpen, M., Philippens, M.E.P., van der Heide, U.A.: Accurate prostate tumour detection with multiparametric magnetic resonance imaging: Dependence on histological properties. Acta Oncol. 53(1), 88–95 (2014)CrossRefGoogle Scholar
  2. 2.
    Cosatto, E., Mille, M., Grad, H.P., Meyer, J.S.: Grading nuclear pleomorphism on histological micrographs. In: 19th Int. Conf. Pattern Recogn. (2008)Google Scholar
  3. 3.
    DiFranco, M.D., O’Hurley, G., Kay, E.W., Watson, W.G., Cunningham, P.: Ensemble based system for whole-slide prostate cancer probability mapping using color texture features. Comput. Med. Imaging Graph. 35, 629–645 (2011)CrossRefGoogle Scholar
  4. 4.
    DiFranco, M.D., Reynolds, H.M., Mitchell, C., Williams, S., Allan, P., Haworth, A.: Performance assessment of automated tissue characterization for prostate H and E stained histopathology. In: SPIE Medical Imaging, p. 94200M (2015)Google Scholar
  5. 5.
    Gibbs, P., Liney, G.P., Pickles, M.D.: Correlation of ADC and T2 measurements with cell density in prostate cancer at 3.0 Tesla. Invest. Radiol. 44(9), 572–576 (2009)CrossRefGoogle Scholar
  6. 6.
    Khan, A.M., Rajpoot, N., Treanor, D., Magee, D.: A nonlinear mapping approach to stain normalization in digital histopathology images using image-specific color deconvolution. IEEE Trans. Biomed. Eng. 61(6), 1729–1738 (2014)CrossRefGoogle Scholar
  7. 7.
    Macenko, M., Niethammer, M., Marron, J.S., Borland, D., Woosley, J.T., Guan, X., Schmitt, C., Thomas, C.: A method for normalizing histology slides for quantitative analysis. In: Proceedings of IEEE ISBI 2009, pp. 1107–1110 (2009)Google Scholar
  8. 8.
    McCann, M.T., Ozolek, J.A., Castro, C.A., Parvin, B., Kovacevic, J.: Automated histology analysis: Opportunities for signal processing. IEEE Signal Process. Mag. 32(1), 78–87 (2015)CrossRefGoogle Scholar
  9. 9.
    Reynolds, H.M., Williams, S., Zhang, A.M., Ong, C.S., Rawlinson, D., Chakravorty, R., Mitchell, C., Haworth, A.: Cell density in prostate histopathology images as a measure of tumor distribution. In: SPIE Medical Imaging, p. 90410S (2014)Google Scholar
  10. 10.
    Ruifrok, A.C., Johnston, D.A.: Quantification of histochemical staining by color deconvolution. Analyt. Quant. Cytol. Histol. 23, 291–299 (2001)Google Scholar
  11. 11.
    Wienert, S., Heim, D., Saeger, K., Stenzinger, A., Beil, M., Hufnagl, P., Dietel, M.,Denkert, C., Klauschen, F.: Detection and segmentation of cell nuclei in virtualmicroscopy images: A minimum-model approach. Scientific Reports 2, 503 (2012)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 2.5 International License (http://creativecommons.org/licenses/by-nc/2.5/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

The images or other third party material in this chapter are included in the chapter's Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the chapter's Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.

Authors and Affiliations

  • Michaela Weingant
    • 1
  • Hayley M. Reynolds
    • 2
    • 3
  • Annette Haworth
    • 2
    • 3
  • Catherine Mitchell
    • 4
  • Scott Williams
    • 5
  • Matthew D. DiFranco
    • 6
    Email author
  1. 1.Vienna University of TechnologyViennaAustria
  2. 2.Department of Physical SciencesPeter MacCallum Cancer CentreMelbourneAustralia
  3. 3.Sir Peter MacCallum Department of OncologyUniversity of MelbourneMelbourneAustralia
  4. 4.Department of PathologyPeter MacCallum Cancer CentreMelbourneAustralia
  5. 5.Division of Radiation Oncology and Cancer ImagingPeter MacCallum Cancer CentreMelbourneAustralia
  6. 6.Center for Medical Physics and Biomedical EngineeringMedical University ViennaViennaAustria

Personalised recommendations